Vercel Sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across c...
概览
The Vercel Sandbox skill enables AI agents to execute browser automation tasks within Vercel Sandbox microVMs. Developed as part of the vercel-labs/agent-browser repository, which has gained significant traction with over 37,000 stars, this tool allows developers to run headless Chrome without the typical binary size constraints found in serverless environments. It is compatible with frameworks like Next.js, SvelteKit, and Nuxt. By leveraging microVM technology, the skill provides a stable environment for persistent browser sessions and complex web interactions. This integration is particularly useful for agents like Codex and Claude that require reliable web navigation capabilities directly from a Vercel-deployed application infrastructure.
使用场景
安装说明
# Review source first
open https://github.com/vercel-labs/agent-browser/blob/main/skill-data/vercel-sandbox/SKILL.mdCopy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.
安全提示
This skill operates within Vercel Sandbox microVMs to isolate browser processes from the main application environment. Users should ensure that any data handled during automated sessions complies with their specific security protocols and Vercel's execution policies.
相关 Skills
Constant Time Testing
trailofbits/skills
通过运行密码学实现来测量其中的时序侧信道,使用 dudect 进行统计分析,并使用基于 Valgrind 的 Timecop 进行动态跟踪。涵盖形式化、符号化、动态和统计类工具以及如何解读结果。适用于测试正在运行的实现是否为恒定时间、测量已编译二进制文件的时间方差,或调查疑似的时序攻击。不适用于静态检查编译器输出——constant-time-analysis 插件
Baoyu Design
JimLiu/baoyu-design
创建精美的设计产出物作为自包含的 HTML:UI 模型、交互原型、线框图、落地页、仪表板、应用界面、移动应用、幻灯片(又名 PPT / PowerPoint 演示文稿)、文档和简历、动画、3D 对象、研究报告、HTML 电子邮件、图表、传单和视觉探索。每当用户要求为界面、产品屏幕、用户流程或内容布局进行设计、制作模型、原型设计、绘制线框图、可视化、探索或制作 PPT/幻灯片时使用。
Managed Deep Agents
langchain-ai/langchain-skills
在通过 mda CLI 于 LangSmith 中构建、测试或部署 Managed Deep Agents 时的 INVOKE THIS SKILL。端到端引导用户完成他们的首个 agent —— 深入沟通其想要构建的内容,将其映射到 MDA 的实际能力上,然后进行脚手架搭建与部署。涵盖基于文件的项目布局;define_deep_agent / defineDeepAgent;instructions、skills、memory、identity、tools、middleware、sandboxes、schedules、channels 和 evals;mda init/build/dev/deploy/logs/delete;
花叔Design · Huashu-Design
mxyhi/ok-skills
花叔Design——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索+设计方向顾问+专家评审。根据任务embody对应专家(UX/动画师/幻灯片设计师/原型师),避免web design tropes。触发词:做原型、交互原型、HTML演示、动画Demo、设计变体、hi-fi设计、UI mockup、prototype、做个HTML页面、做个可视化、app原型、iOS原型、导出MP4/GIF、60fps视频、设计风格、设计方向、配色方案、推荐风格、选个风格、做个好看的、评审、好不好看、review this design、带解说的动画、解说视频、长视频科普、voiceover、narration、5分钟讲清楚什么是X
GSAP Core
mxyhi/ok-skills
核心 API 的官方 GSAP skill —— 包含 gsap.to()、from()、fromTo()、easing、duration、stagger、defaults、gsap.matchMedia()(响应式、prefers-reduced-motion)。当用户请求 JavaScript 动画库、React/Vue/vanilla 中的动画、GSAP 补间动画、缓动、基础动画、响应式或减弱动态效果 a 时使用。
Design Audit
tinh2/skills-hub-registry
全面自主的设计质量审查,涵盖无障碍访问(WCAG 2.2)、性能、主题化、响应式/自适应设计以及反模式检测。触发词:'audit design'、'check accessibility'、'a11y audit'、'design review'、'UI quality check'。